Automated identification of defect morphology and spatial distribution in woven composites

Anna Madra, Dan Thuy Van-Pham, Minh Tri Nguyen, Chanh Nghiem Nguyen, Piotr Breitkopf, François Trochu

Research output: Contribution to journalArticlepeer-review

2 Scopus citations


The performance of heterogeneous materials, for example, woven composites, does not always reach the predicted theoretical potential. This is caused by defects, such as residual voids introduced during the manufacturing process. A machine learning-based methodology is proposed to determine the morphology and spatial distribution of defects in composites based on X-ray microtomographic scans of the microstructure. A concept of defect "genome" is introduced as an indicator of the overall state of defects in the material, enabling a quick comparison of specimens manufactured under different conditions. The approach is illustrated for thermoplastic composites with unidirectional banana fiber reinforcement.

Original languageEnglish (US)
Article number178
JournalJournal of Composites Science
Issue number4
StatePublished - 2020

All Science Journal Classification (ASJC) codes

  • Ceramics and Composites
  • Engineering (miscellaneous)


Dive into the research topics of 'Automated identification of defect morphology and spatial distribution in woven composites'. Together they form a unique fingerprint.

Cite this